Reading up on prompt-engineering
17 deep · digging since nov 25, 25
- The Problem is Prompt Debt
Hand-tuning natural language prompts for AI systems accumulates debt that slows iteration, locks teams to one model, and should be replaced with metrics, tests, and automated prompt optimization.
- Prompt Engineering Is Permanent
Better AI models didn't eliminate prompt engineering but transformed it into a systems discipline involving context, tool use, and production reliability.
- Changes in the system prompt between Claude Opus 4.6 and 4.7
Opus 4.7's system prompt adds child safety tags, a tool-search mechanism, anti-verbosity instructions, and drops the Trump presidency clarification from the 4.6 prompt.
- Caveman: Why use many token when few token do trick
Caveman is an open-source Claude skill that forces LLMs to reply in terse, ungrammatical speech, cutting output tokens by up to 65% while preserving answer quality.
- AddyOsmani.com - How to write a good spec for AI agents
Writing effective AI agent specs requires a high-level vision, structured PRD-like format, modular task breakdowns, and built-in guardrails to keep agents focused and productive.
- What Actually Is Claude Code’s Plan Mode?
Claude Code's plan mode is a thin prompt overlay and read-only guard, not a fundamentally different execution path.
- GPT-5.1-Codex-Max Prompting Guide
OpenAI recommends migrating to the Codex-Max agentic model using the codex-cli prompt, compacted context, and specific tools for best performance on complex coding tasks.
- Claude Agent Skills: A First Principles Deep Dive
Claude's Agent Skills use a prompt-based meta-tool architecture that injects specialized instructions and context modifications to guide complex workflows without executing code.
Takes
Asked Claude to design my logo. The result looked like it cost $500,000. It cost $0. The 7 prompts I used (steal these): Save for later🔖
@ElsaSofia__AI
My chief of SEO, Claude Cowork Fable 5
@bloggersarvesh
I’ve found the most important part of working with Fable is discovering my own unknowns so I can prompt it better, heres how I do that.
@trq212
New skill: /animation-vocabulary Helps you get better animations from an AI by telling it exactly what you want by using the right words. "morph", "rubber-banding", "layout animation", and more.
@emilkowalski
The 6 MOST valuable skills to learn in the AGENTIC era and how to learn them (clearly explained in 29 minutes)
@gregisenberg
if you want to design with AI agents, these skills are amazing - impeccable
@nurijanian
Current AI custom prompt: You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can. Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.
@pmarca
CRITICAL: EVERYONE USING CLAWDBOT SHOULD RUN THIS PROMPT RIGHT NOW:By default, the 2 best Clawd memory features are turned OFFRunning this 1 prompt will immediately stop your AI from getting confused in between compactions/sessions:Prompt:"Enable memory flush before…
@AlexFinn
https://t.co/4hDRinAaLz
@VibeMarketer_